Arc Search vs PropensityAI

Arc Search is a free browser centered on Browse for Me, which searches multiple pages and produces an answer on a custom webpage. Its built-in blocker is described as stopping ads, trackers, pop-ups, and cookie banners. Other features include reader mode, incognito mode, website translation, and voice search. Inactive tabs are archived automatically, with help documentation listing intervals from 12 hours to 30 days. Browse for Me is the default search option; alternatives include Google, Bing, DuckDuckGo, Ecosia, Perplexity, and Kagi. Arc Sync can share desktop Spaces, pinned tabs, and Today tabs with Arc Search on iOS, but is unavailable on Android, and tabs created in Arc Search do not sync back to desktop. The maker says Browse for Me sends command-bar and search-result content to OpenAI to generate summaries. Arc Search supports iOS 16 or later and Android 10 or later. The maker also says Sync sidebar data uses end-to-end encryption, but the product is not currently SOC 2 or ISO 27001 certified and does not offer account MFA.

PropensityAI combines retrieval and reasoning to answer questions across web pages, documents, and media with concise inline citations. It links claims to sources, flags uncertainty, and can decline when evidence is insufficient. Image analysis includes OCR, captioning, visual question answering, and structured extraction. Audio tools transcribe, identify speakers, summarize, and extract tasks. Video search locates scenes and spoken content with time-range citations. Users can query research PDFs and citations, then compare methods, results, and limitations. The maker describes connectors for shared drives, wikis, ticketing systems, and internal documents. Starter costs nothing, needs no sign-up, and allows up to 16 sources and one file per query. Local packages cost €8,000 as a one-time purchase for 30B Science & Logic or 30B Software Engineering, and €20,000, paid once for 130B General Intelligence. Team and Enterprise plans add shared connectors, controls, analytics, on-premises or VPC deployment, governance, and support. Enterprise can run local systems inside customer infrastructure, including air-gapped environments. The site says private queries and uploads are not used to train foundation models.